Agentic Visualization: Extracting Agent-based Design Patterns from Visualization Systems

TL;DR

This paper introduces agentic visualization by analyzing existing systems with AI components, extracting design patterns that balance automation with human control to enhance analytical capabilities.

Contribution

It reinterprets visualization systems through an agentic lens and identifies key design patterns for integrating AI agents while preserving human agency.

Findings

Extracted design patterns for agentic visualization

Identified roles, communication, and coordination strategies

Provided a foundation for future AI-enhanced visualization systems

Abstract

Autonomous agents powered by Large Language Models are transforming AI, creating an imperative for the visualization field to embrace agentic frameworks. However, our field's focus on a human in the sensemaking loop raises critical questions about autonomy, delegation, and coordination for such \textit{agentic visualization} that preserve human agency while amplifying analytical capabilities. This paper addresses these questions by reinterpreting existing visualization systems with semi-automated or fully automatic AI components through an agentic lens. Based on this analysis, we extract a collection of design patterns for agentic visualization, including agentic roles, communication and coordination. These patterns provide a foundation for future agentic visualization systems that effectively harness AI agents while maintaining human insight and control.